用于决策聚焦学习的局部凸全局损失网络
Locally Convex Global Loss Network for Decision-Focused Learning
AI总结:
针对决策聚焦学习中计算最优决策梯度的挑战及现有方法适用域受限问题,提出局部凸全局损失网络LCGLN,通过部分输入凸神经网络实现通用DFL的单一替代损失,经三个随机决策问题验证其有效性与灵活性。
摘要:
在不确定性下的决策问题中,预测未知参数通常被视为与优化部分相互独立。决策聚焦学习(DFL)是一种面向任务的框架,它通过调整预测模型为相应任务提供更好的决策,从而整合预测与优化。在此过程中,计算最优决策相对于参数的梯度时会出现一个不可避免的挑战。现有研究通过平滑重构替代优化或构建模仿任务损失的替代损失函数来应对这一问题,但这些方法适用于受限的优化域。本文提出局部凸全局损失网络(LCGLN),这是一种可在通用DFL范式中实现的全局替代损失模型。LCGLN通过部分输入凸神经网络学习任务损失,该网络对选定输入保证是凸的,同时对其他输入保持非凸全局结构。这使得LCGLN只需通过单一替代损失即可支持通用DFL,无需选择合适的参数形式。我们通过在三个随机决策问题上评估所提出的模型,证实了LCGLN的有效性和灵活性。
英文摘要:
In decision-making problems under uncertainty, predicting unknown parameters is often considered independent of the optimization part. Decision-focused learning (DFL) is a task-oriented framework that integrates prediction and optimization by adapting the predictive model to give better decisions for the corresponding task. Here, an inevitable challenge arises when computing the gradients of the optimal decision with respect to the parameters. Existing research copes with this issue by smoothly reforming surrogate optimization or constructing surrogate loss functions that mimic task loss. However, they are applied to restricted optimization domains. In this paper, we propose Locally Convex Global Loss Network (LCGLN), a global surrogate loss model that can be implemented in a general DFL paradigm. LCGLN learns task loss via a partial input convex neural network which is guaranteed to be convex for chosen inputs while keeping the non-convex global structure for the other inputs. This enables LCGLN to admit general DFL through only a single surrogate loss without any sense for choosing appropriate parametric forms. We confirm the effectiveness and flexibility of LCGLN by evaluating our proposed model with three stochastic decision-making problems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。